© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17128
    Prev
    Next
    INDEX
    Explanations

    rounded shapes and numerical rounding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    atica
    -0.17
    ä¸įä¸ĭ
    -0.17
    ories
    -0.17
    ä¸ĢçĤ¹éĥ½ä¸į
    -0.16
    oking
    -0.16
    sst
    -0.15
     âĦķ
    -0.15
    åŁĴ
    -0.15
    napshot
    -0.15
    å¤ľéĩĮ
    -0.15
    POSITIVE LOGITS
    0.23
     Jub
    0.19
    yna
    0.17
    -priced
    0.17
    eds
    0.17
     tÆ°á»Ŀng
    0.16
    kur
    0.16
    rox
    0.16
    edly
    0.16
    pek
    0.16
    Activations Density 0.016%

    No Known Activations